AI may improve suicide prevention in the future

Dejected - Depressed

Credit: Unsplash/CC0 Public Domain

The loss of any life can be devastating, but the loss of life by suicide is especially tragic.

About nine Australians take their own lives every day, and it is the leading cause of death for Australians aged 15-44. Suicide attempts are more common, with some estimates suggesting they occur up to 30 times more often than deaths.

“Suicide has significant effects when it occurs. It affects many people and has far-reaching consequences for family, friends and communities,” says Karen Kusuma, PhD, at the University of New South Wales in Sydney. Candidate in psychiatry at the Black Dog Institute, which investigates suicide prevention in adolescents.

Ms. Kusuma and a team of researchers from the Black Dog Institute and the Big Data Research Center in Health recently investigated the evidence base of machine learning models and their ability to predict future suicidal behavior and thoughts. They evaluated the performance of 54 machine learning algorithms previously developed by researchers to predict suicide-related outcomes from thought, attempt, and death.

A meta-analysis published in Journal of Psychological Researchfound that machine learning models outperformed traditional risk prediction models in predicting suicide-related outcomes, which have traditionally performed poorly.

“Overall, the results show that there is a preliminary but compelling evidence base that machine learning can be used to predict future outcomes related to suicide with very good performance,” says Ms. Kusuma.

Conventional suicide risk assessment models

Identification of individuals at risk of suicide is essential to preventing and managing suicidal behaviors. However, predicting the risks is difficult.

In emergency departments (EDs), risk assessment tools such as questionnaires and rating scales are commonly used by clinicians to identify patients at high risk of suicide. However, evidence suggests that it is ineffective in accurately predicting suicide risk Doing excercise.

“While there are some common factors that appear to be linked to suicide attempts, the profile of the risk for one person may appear very different to another,” Ms Kusuma says. “But suicide is complex, with many dynamic factors that make it difficult to assess the risk profile using this assessment process.”

A post-mortem analysis of people who died by suicide in Queensland found that of those who received a formal suicide risk assessment, 75% were classified as low risk, and none were classified as high risk. Previous research examining the past 50 years of quantitative prediction models for suicide risk found that they were slightly better than chance at predicting future suicide risk.

“Suicide is the leading cause of years of life lost in many parts of the world, including Australia. But the way suicide risk is assessed has not developed recently, and we have not seen a significant reduction in deaths from suicide. In some years, we have We saw increases.

Despite the lack of evidence in favor of traditional suicide risk assessments, its management remains standard practice in health care settings to determine the level of patient care and support. Those identified as high risk usually receive the highest level of care, while those identified as low risk are discharged from hospital.

“With this approach, unfortunately, high-level interventions are not being offered to people who really need help,” says Ms. Kusuma. “So we should look to overhaul the process and explore ways we can improve suicide prevention.”

Machine learning suicide screening

Ms. Kusuma says there is a need for more innovation in suicide science and a reassessment of standard models for predicting suicide risk. Efforts to improve risk prediction have led to the use of her research Artificial intelligence (AI) to develop suicide risk algorithms.

“Having an AI that can take in far more data than a clinician would be able to better recognize patterns associated with suicide risk,” says Ms. Kusuma.

In the meta-analysis study, machine learning models outperformed criteria previously defined by traditional clinical, theoretical, and statistical suicide risk prediction models. They correctly predicted 66% of people who would experience the outcome of suicide and correctly predicted 87% of people who would not experience the outcome of suicide.

“Machine learning models can predict suicide death well compared to traditional prediction models and can become an efficient and effective alternative to traditional risk assessment‘ says Mrs. Kusuma.

The strict assumptions of traditional statistical models do not link machine learning models. Alternatively, it can be flexibly applied to large data sets to model the complex relationships between several risk factors and suicidal outcomes. They can also integrate responsive data sources, including social media, to identify peaks of suicide risk and reporting times where interventions are most needed.

“Over time, machine learning models can be configured to take in more complex and larger data to better identify patterns associated with suicide risk,” says Ms. Kusuma.

The use of machine learning algorithms to predict suicide-related outcomes is still an emerging area of ​​research, with 80% of identified studies being published in the past five years. Ms Kusuma says future research will also help address the risks of aggregation bias present in computational models so far.

“Further research is necessary to improve and validate these algorithms, which will then help advance the application machine learning On the science of suicide, says Ms. Kusuma. “While we are still far from implementation in a clinical setting, research indicates that this is a promising way to improve the accuracy of suicide risk screening in the future.”

Treating suicide risk in people with mental disorders

more information:
Karen Kusuma et al, Performance of machine learning models in predicting suicidal thoughts, attempts, and mortality: a meta-analysis and systematic review, Journal of Psychological Research (2022). DOI: 10.1016 / j.jpsychires.2022.09.050

the quote: Artificial Intelligence May Improve Suicide Prevention in the Future (2022, October 5) Retrieved October 5, 2022 from

This document is subject to copyright. Notwithstanding any fair dealing for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.

Leave a Comment